--- title: "agents-from-scratch vs core" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/pguso-agents-from-scratch-vs-redplanethq-core" tools: ["pguso-agents-from-scratch", "redplanethq-core"] --- # agents-from-scratch vs core *GraphCanon updated Sep 20, 2026* ## Verdict Pick agents-from-scratch if agents-from-scratch is for those who want absolute control over their AI agent development using only local resources and Python, focusing on deep learning without relying on external frameworks or cloud dependencies; pick core if redPlanetHQ/core offers an AI framework for personalized assistants focusing on ai-agent capabilities, ai-memory, and automation. It is self-hosted and open-source under the AGPL. [agents-from-scratch](https://github.com/pguso/agents-from-scratch) reports 1.0k GitHub stars, 251 forks, and 4 open issues, last pushed Jul 25, 2026. [core](https://getcore.me) has 2.0k stars, 194 forks, and 211 open issues, last pushed Sep 7, 2026. Figures are from public GitHub metadata via [agents-from-scratch's repository](https://github.com/pguso/agents-from-scratch) and [core's repository](https://github.com/RedPlanetHQ/core). | | [agents-from-scratch](/tools/pguso-agents-from-scratch.md) | [core](/tools/redplanethq-core.md) | | --- | --- | --- | | Tagline | Build AI agents locally without relying on frameworks or cloud APIs. | Your Personal AI OS | | Stars | 1,017 | 1,985 | | Forks | 251 | 194 | | Open issues | 4 | 211 | | Language | Python | TypeScript | | Adopt for | agents-from-scratch is for those who want absolute control over their AI agent development using only local resources and Python, focusing on deep learning without relying on external frameworks or cloud dependencies. | RedPlanetHQ/core offers an AI framework for personalized assistants focusing on ai-agent capabilities, ai-memory, and automation. It is self-hosted and open-source under the AGPL 3.0 license. | | Persona | - | - | | Runtime | - | - | | License | MIT License: Permissive licensing allowing free use and distribution for both commercial and non-commercial purposes. | Other | | Categories | AI Agents, Developer Tools | AI Agents, Developer Tools | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [agents-from-scratch](/tools/pguso-agents-from-scratch.md) | [core](/tools/redplanethq-core.md) | | --- | --- | --- | | Maintenance | Steady (60%) | Active (82%) | | Days since push | 56d | 12d | | Open issues (now) | 4 | 211 | | Stars delta | +63 (30d) | +38 (30d) | | Open issues delta | +1 (30d) | +3 (30d) | | Owner type | User | Organization | | Full report | [trust report](/tools/pguso-agents-from-scratch/trust.md) | [trust report](/tools/redplanethq-core/trust.md) | ## Decision facts: agents-from-scratch - **Requirements:** Min 8 GB RAM; Local large language model availability is critical as the tool does not utilize any cloud APIs. - **Adopt for:** agents-from-scratch is for those who want absolute control over their AI agent development using only local resources and Python, focusing on deep learning without relying on external frameworks or cloud dependencies. - **License detail:** MIT License: Permissive licensing allowing free use and distribution for both commercial and non-commercial purposes. ## Decision facts: core - **Adopt for:** RedPlanetHQ/core offers an AI framework for personalized assistants focusing on ai-agent capabilities, ai-memory, and automation. It is self-hosted and open-source under the AGPL 3.0 license. ## Choose when ### Choose agents-from-scratch if… - agents-from-scratch is primarily Python; core is TypeScript. - License: agents-from-scratch is MIT, core is Other. - Requirements: Min 8 GB RAM; Local large language model availability is critical as the tool does not utilize any cloud APIs.. - Tags unique to agents-from-scratch: agent-architecture, ai-agents, llm, local-llm. - You plan to teach yourself or others about the fundamentals of creating AI agents from ground zero with complete transparency into each layer of architecture. ### Choose core if… - core is primarily TypeScript; agents-from-scratch is Python. - License: core is Other, agents-from-scratch is MIT. - Tags unique to core: ai-agent, ai-memory, automation, automations. - When you require a personalized AI assistant that can integrate with multiple services you use daily. ## When NOT to use agents-from-scratch - You are working on an application that needs to be deployed quickly. The tool's approach from first principles can be time-consuming compared to using established frameworks. - If you need scalability or cloud capabilities such as easy scaling with demand, this tool will not provide these features since it strictly operates on local infrastructure. ## When NOT to use core - If you prefer cloud-based solutions over self-hosted options as RedPlanetHQ/core requires local hosting to ensure data privacy and control. - When looking for a chatbot that operates on-demand instead of an AI assistant that is constantly active in the background. ## Common questions ### What is the difference between agents-from-scratch and core? agents-from-scratch: Build AI agents locally without relying on frameworks or cloud APIs.. core: Your Personal AI OS. See the comparison table for live GitHub stats and shared categories. ### When should I choose agents-from-scratch over core? Choose agents-from-scratch over core when agents-from-scratch is primarily Python; core is TypeScript; License: agents-from-scratch is MIT, core is Other; Requirements: Min 8 GB RAM; Local large language model availability is critical as the tool does not utilize any cloud APIs.; Tags unique to agents-from-scratch: agent-architecture, ai-agents, llm, local-llm; You plan to teach yourself or others about the fundamentals of creating AI agents from ground zero with complete transparency into each layer of architecture. ### When should I choose core over agents-from-scratch? Choose core over agents-from-scratch when core is primarily TypeScript; agents-from-scratch is Python; License: core is Other, agents-from-scratch is MIT; Tags unique to core: ai-agent, ai-memory, automation, automations; When you require a personalized AI assistant that can integrate with multiple services you use daily. ### When should I avoid agents-from-scratch? You are working on an application that needs to be deployed quickly. The tool's approach from first principles can be time-consuming compared to using established frameworks. If you need scalability or cloud capabilities such as easy scaling with demand, this tool will not provide these features since it strictly operates on local infrastructure. ### When should I avoid core? If you prefer cloud-based solutions over self-hosted options as RedPlanetHQ/core requires local hosting to ensure data privacy and control. When looking for a chatbot that operates on-demand instead of an AI assistant that is constantly active in the background. ### Is agents-from-scratch or core more popular on GitHub? core has more GitHub stars (1,985 vs 1,017). Stars measure visibility, not whether either tool fits your constraints. ### Are agents-from-scratch and core open source? Yes - both are open-source projects on GitHub (agents-from-scratch: MIT, core: Other). ### Where can I find alternatives to agents-from-scratch or core? GraphCanon lists graph-backed alternatives at [agents-from-scratch alternatives](/tools/pguso-agents-from-scratch/alternatives) and [core alternatives](/tools/redplanethq-core/alternatives) ([agents-from-scratch markdown twin](/tools/pguso-agents-from-scratch/alternatives.md), [core markdown twin](/tools/redplanethq-core/alternatives.md)), ranked by typed relationship edges rather than popularity votes. ### Is there a machine-readable version of this comparison? Yes. The markdown twin at [this comparison](/compare/pguso-agents-from-scratch-vs-redplanethq-core.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, agents-from-scratch or core? agents-from-scratch: Steady. core: Active. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance. ### Where are the full trust reports for agents-from-scratch and core? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [agents-from-scratch trust report](/tools/pguso-agents-from-scratch/trust); [core trust report](/tools/redplanethq-core/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=pguso-agents-from-scratch`](/api/graphcanon/graph?tool=pguso-agents-from-scratch) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_